Recent advances in large language models (LLMs) have enabled promising progress in diagnosis prediction from electronic health records (EHRs). However, existing LLM-based approaches tend to overfit to historically observed diagnoses, often overlooking novel yet clinically important conditions that are critical for early intervention. To address this, we propose EviCare, an in-context reasoning framework that integrates deep model guidance into LLM-based diagnosis prediction. Rather than prompting LLMs directly with raw EHR inputs, EviCare performs (1) deep model inference for candidate selection, (2) evidential prioritization for set-based EHRs, and (3) relational evidence construction for novel diagnosis prediction. These signals are then composed into an adaptive in-context prompt to guide LLM reasoning in an accurate and interpretable manner. Extensive experiments on two real-world EHR benchmarks (MIMIC-III and MIMIC-IV) demonstrate that EviCare achieves significant performance gains, which consistently outperforms both LLM-only and deep model-only baselines by an average of 20.65% across precision and accuracy metrics. The improvements are particularly notable in challenging novel diagnosis prediction, yielding average improvements of 30.97%.

Full fine-tuning of large vision-language models (VLMs) for cross-modal retrieval is computationally expensive and prone to overfitting. Adapter-based parameter-efficient transfer learning offers a practical alternative, but existing designs often suffer from structural redundancy and the loss of fine-grained visual details critical for accurate matching. These limitations are particularly detrimental for retrieval, which demands fine-grained perceptual discrimination beyond semantic alignment. To address these challenges, we propose B-HFA, a parameter-efficient framework for vision-language retrieval. B-HFA introduces a Block-wise Shared Adapter (B-Adapter) to reduce redundancy through structured parameter sharing, and a Hierarchical Feature Aggregation (HFA) module that dynamically integrates intermediate visual features guided by textual semantics. This design enables efficient adaptation while preserving visual fidelity essential for retrieval. Extensive experiments on multiple retrieval benchmarks demonstrate that B-HFA achieves competitive performance with only 0.13% of trainable parameters. Moreover, its competitive results on visual question answering suggest the generality of the proposed framework beyond retrieval tasks.

Sequential recommendation has achieved remarkable success across various application domains due to its ability to capture dynamic user preferences. Therefore, its effectiveness significantly diminishes in user cold-start scenarios, where new users have limited or no interaction history. Current solutions typically design specialized model architectures to infer cold-start user preferences from auxiliary information, such as user attributes or social networks. However, such methods overlook compatibility with advanced sequential recommender models, preventing the efficient extraction of sequential features. To address this limitation, we propose CDMRec, a Causal Diffusion Preference Model for user cold-start sequential recommendation. CDMRec generates diffusion-based preference representations for cold-start users, which can be directly utilized by existing sequential recommendation models. The framework first constructs a Preference-Dominant Sequence (PDS) by isolating interactions most indicative of user interests, mitigating noise from irrelevant behaviors. Then, leveraging causal inference, CDMRec identifies key causal variables from PDS to condition the diffusion process, enabling the generation of personalized behavioral preferences. Extensive experiments on three public datasets demonstrate that CDMRec can be seamlessly integrated into mainstream sequential recommender models, yielding substantial performance gains in cold-start settings.

Contrastive learning has emerged as a promising paradigm by inherently generating self-supervised signals and uncovering latent patterns from interaction data to enhance recommendation performance. However, most current graph contrastive learning-based recommendation methods rely on random augmentation strategies,which may disrupt graph structural information and compromise model robustness. In addition, long-tail items suffer from insufficient exposure, making it difficult to learn high-quality feature rep- resentations, ultimately degrading recommendation effectiveness.To overcome these limitations, this paper presents DDGCL, a dual diffusion-based graph contrastive learning method. A contrastive view optimization module is designed, which employs singular value decomposition to perform low-rank approximation on the interaction graph, efficiently extracting global structural features while accelerating the diffusion process. The diffusion model then performs noise addition and denoising on this basis to generate contrastive views that preserve graph structural information. In addition, a method for embedding augmentation designed for long-tail items is proposed. This module utilizes a conditional diffusion model, where global graph information serves as conditional con- straints to guide the denoising process of long-tail items, thereby improving their representation learning. A comprehensive evaluation on multiple public benchmark datasets demonstrates that DDGCL significantly outperforms various baseline models, validating the effectiveness of the proposed approach.

Sequential recommendation aims to predict the next user interaction by modeling historical behavior sequences. Recently diffusion models (DMs) have emerged as a promising generative approach due to their robustness and capacity for uncertainty modeling. However, existing diffusion-based recommendation approaches still encounter two major challenges: sample drift during the noise injection process, which compromises the stability of generation; and limited adaptability to noisy data, which hampers the effectiveness of personalized recommendations. To address these issues, we propose GSDiffRec, a novel generative sequential recommendation approach that integrates two core modules: (i) Semantic-Targeted Guidance Module (STG) built upon an enhanced Transformer backbone equipped with shaped attention and convolutional components to improve representational efficiency and modeling capacity; and (ii) Geodesic Diffusion Module (GDM) enforcing manifold constraints through geodesic random walks, thereby preserving geometric consistency and enhancing denoising stability throughout the diffusion process. Extensive experiments on two public Amazon datasets demonstrate that GSDiffRec significantly outperforms a wide range of competitive baselines. Further ablation studies validate the complementary contributions and effectiveness of the GDM and STG modules.

Abnormal user detection has been a critical and widely studied research problem in social networks since these users can create significant risks to platform security and privacy leakage. Currently, graph-based models are commonly used for exploring the structured social network data and temporally dynamic user interactions, leading to significant advances in dynamic heterogeneous graph-based abnormal user detection. However, most existing approaches are correlation-driven and lack the ability to separate stable patterns from transient noise. Furthermore, these methods are highly dependent on inherent labels and fail to detect common few-shot anomalies in social networks. To address these issues, we propose CIFAD, a Causal-Invariant Few-shot Anomaly Detection method that improves few-shot anomaly detection with an active annotation strategy. Specifically, CIFAD first integrates a sparse lagged attention encoder to model multi-relational temporal interactions. Furthermore, it introduces causal-invariant subspace decomposition to disentangle stable causal signals from dynamic environmental noise and improve generalization. Finally, it designs an active annotation strategy based on influence functions and coverage optimization to maximize the utility of limited labels in a closed-loop process. Extensive experiments on multiple real-world social network datasets demonstrate that our method achieves higher accuracy than state-of-the-art methods, validating its robustness in abnormal user detection for social networks.

With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.

Multi-modal recommendation has become essential with the rapid expansion of online platforms such as e-commerce and video-sharing applications. In this work, we focus on the Multi-Modal New Item Recommendation (MMNIR) problem, where items with multi-modal content but newly introduced items lack interaction history. The MMNIR problem is particularly challenging in two aspects: (1) a large number of new items are created rapidly over time without any interaction data, (2) not all existing interactions are equally useful, and it is non-trivial to identify informative behaviors from users with similar preferences. However, previous methods fail to identify users with similar preferences and to capture informative behaviors from historical data. Furthermore, conventional models primarily rely on simple co-occurring signals, leading to spurious neighbors and neglecting the informative behaviors of truly similar users with consistent preferences. To fill this gap, we propose Joint Similar User Exploration and Informative Behavior Guidance (SuperG) for solving the MMNIR problem. SuperG first proposes a similar user exploration module to identify users with similar preferences to the target user. Then it incorporates an informative behavior mining module to retrieve informative behaviors from both the target user and similar users' histories to support new item recommendation. Finally, SuperG proposes a behavior-guided hybrid recommendation module to incorporate the retrieved behavioral signals to guide the recommendation of new items. Our empirical study on three real datasets demonstrates that SuperG outperforms the state-of-the-art models under the MMNIR setting.

Web-scale platforms and online services rely on log-based anomaly detection to safeguard availability, latency SLOs, and user experience. In real-world web interactions, system logs often exhibit irregular temporal intervals, bursty densities, and heterogeneous semantics, which pose significant challenges for log anomaly detection. Existing methods such as LSTM and Transformer assume a fixed input window, which conflicts with the inherently irregular nature of system logs. Moreover, most prior works build a single-view representation, overlooking the multi-relational nature of logs. To overcome these challenges, we propose DyLogNet, a dynamic multi-relational graph framework for log anomaly detection. Specifically, this framework constructs a density-aware dynamic graph with variable-length windows, and represents logs from three relational perspectives: temporal co-occurrence, semantic similarity, and anomaly tendency. Next, we design a cross-layer attention mechanism that integrates heterogeneous structures to highlight the most relevant relations and enhance event representations. Furthermore, a cross-snapshot memory injection module updates global memory through a recurrent unit and injects it into current graph representations via an affine transformation, enabling temporal continuity. Experiments on three public log datasets demonstrate that DyLogNet outperforms state-of-the-art methods, especially in few-shot scenarios.

Hash-based collaborative filtering (Hash-CF) approaches recently employ efficient Hamming distance of learned binary representations to accelerate recommendations. Benefiting from its probabilistic nature, Variational Autoencoder (VAE) enables robust Hash-CF with stronger generalization ability. However, VAE-based Hash-CF still faces two challenging problems: 1) Traditional VAE urges the latent variables of different users (or items) to fit a unified and monotonous prior distribution, and lacks considerations for distinctive characteristics of users (or items). The obtained representations of users and items with slight individual differentiation may further weaken the performance of Hash-CF for subsequent personalized recommendations. 2) Hash-CF under the VAE framework requires discrete optimization on latent Bernoulli distributions, which are discrete and NP-hard to optimize. In this paper, we propose a Dual Discrete Collaborative Filtering (DDCF) approach, including a cluster-enhanced representation generation module and a CNF-enabled discrete optimization module. The former module mainly develops cluster-aware latent space to generate discriminative representations for users or items with significantly different characteristics. The latter module employs Continuous Normalizing Flow (CNF) to achieve discrete optimization on latent Bernoulli distributions steadily and effectively. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our DDCF compared with the state-of-art methods in terms of effectiveness and efficiency.

Trust relationships play a crucial role in various domains, such as social spam detection, retweet behavior analytics, and recommendation systems. Trust is often implicit and difficult to observe directly in the real world, as it is driven by people's underlying intentions and motivations. Therefore, when evaluating trust, it is critical to analyze not only user behavior data but also the intentions behind these behaviors that lead to trust. Existing trust evaluation methods often neglect the underlying reasons behind connections, such as shared hobbies or belonging to the same community. Therefore, these methods cannot differentiate the genuine intentions that lead to trust, resulting in an inaccurate evaluation of hidden trust relationships. To address this issue, we propose a novel Intent-based model for Trust Evaluation (INTRUST). This model can distinguish the intent behind high-order information in social communities using hypergraphs. Initially, we used hyperedges to represent high-order correlations between user-to-item and user-to-user interactions. Then, we construct K intent prototypes, which serve as foundational elements to build trust. Furthermore, we distinguish K-independent intent subgraphs from these high order correlations. To enhance the generalization and robustness of the model, we employ self-supervised learning and construct contrastive views at the node-level, hyperedge-level, and node hyperedge-level. Extensive experiments on real-world datasets demonstrate that our model outperforms state-of-the-art approaches in terms of trust evaluation accuracy and efficiency.

API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.

This is an erratum for the article “Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation” published in ACM Trans. Inf. Syst. 44, 1, Article 27 (December 2025), 30 pages.

The emerging reasoning ability of large language models (LLMs) and accompanying commercial applications offer a promising path for service providers to deploy intelligent agents on their own products through API calls. However, the black-box nature of LLMs has driven providers to try prompt tuning to improve reasoning quality for competitiveness, while the generated reasoning logic results in additional service costs. Although some works have proposed collaborating LLMs and Small Language Models (SLMs) to reduce the frequency of LLM calls, most overlook the actual number of tokens interacting with the LLMs, which results in a potentially high cost still. Furthermore, directly compressing the prompt to reduce tokens often leads to a significant accuracy loss. To address the above challenges, we propose a cost-aware approach for collaborating LLMs and SLMs, named Coco. In our method, a confidence-based task assignment method is designed which leverages the result confidence of SLMs to assess task complexity and determine whether LLM involvement is necessary. For complex tasks, the SLM adapts the input by compressing unnecessary information according to confidence. Considering the potential loss of accuracy, prompt tuning-based reasoning optimization methods are introduced to guide the LLM in generating both the reasoning logic sketch and the final result. Finally, logic alignment is applied to fuse sketches from both models, ensuring the rationality of the reasoning logic. Experimental results on three open-source datasets demonstrate that our approach effectively reduces the cost of API calls to LLMs while ensuring the reasoning accuracy and the reasonableness of generated logic.

Time series forecasting has significant applications across various domains, including industry, agriculture, and finance. Transformer-based models have shown significant promise in enhancing time series forecasting over the past few years. However, existing methods struggle to simultaneously capture local details and global semantics under single-view architectures. They also find it difficult to dynamically adapt to time-varying and multi-scale temporal patterns while accurately modeling the complex, time-varying relationships between multiple variables. To address these challenges, we propose HRCformer, a novel Transformer-based framework that introduces two key innovations: the Hierarchical Recursive Interaction Convolution (HRIC) and the Triad Adaptive Recalibration Module (TARM). HRIC achieves joint modeling of fine-grained short-term fluctuations and high-order cross-period dependencies in time series by integrating Divide-and-Process Convolution for local processing with Recursive Channel Interaction Convolution for global processing. TARM further enhances dynamic modeling via Dynamic Variance Attention, which amplifies critical temporal deviations through 3D attention, and the Adaptive Multivariate Recalibration, which uses a two-layer fully connected network with nonlinear activation to learn the dynamic relationships between channels, suppresses noise, and emphasizes informative multivariate interactions. Comprehensive experiments conducted on seven real-world datasets highlight the superiority of HRCformer compared to prior state-of-the-art methods.

Next Point-of-Interest (POI) recommendation has become a crucial task in Location-Based Social Networks (LBSNs), which provide personalized recommendations by predicting the user's next check-in locations. Commonly used models including Recurrent Neural Networks (RNNs) and Graph Convolutional Networks (GCNs) have been widely explored. However, these models face significant challenges, including the difficulty of capturing the hierarchical and tree-like structure of POIs in Euclidean space and the sparsity problem inherent in POI recommendations. To address these challenges, we propose a Hyperbolic Variational Graph Auto-Encoder (HVGAE) for next POI recommendation. Specifically, we utilize a Hyperbolic Graph Convolutional Network (Hyperbolic GCN) to model hierarchical structures and tree-like relationships by converting node embeddings from euclidean space to hyperbolic space. Then we use Variational Graph Auto-Encoder (VGAE) to convert node embeddings to probabilistic distributions, enhancing the capture of deeper latent features and providing a more robust model structure. Furthermore, we combine the Mamba4Rec recommender and Rotary Position Embedding (RoPE) and propose Rotary Position Mamba (RPMamba) to effectively utilize POI embeddings rich in sequential information, which improves the accuracy of the next POI recommendation. Extensive experiments on three public datasets demonstrate the superior performance of the HVGAE model.

Click-through rate (CTR) prediction is a crucial task in personalized information retrievals, such as industrial recommender systems, online advertising, and web search. Most existing CTR Prediction models utilize explicit feature interactions to overcome the performance bottleneck of implicit feature interactions. Hence, deep CTR models based on parallel structures (e.g., DCN, FinalMLP, xDeepFM) have been proposed to obtain joint information from different semantic spaces. However, these parallel subcomponents lack effective supervision and communication signals, making it challenging to efficiently capture valuable multi-views feature interaction information in different semantic spaces. To address these issues, we propose a simple yet effective novel CTR model: Contrast-enhanced Through Network (CETN). Drawing inspiration from sociology, CETN leverages the complementary nature of diversity and homogeneity to guide the model in acquiring higher-quality feature interaction information. Specifically, CETN employs product-based feature interactions and the augmentation (perturbation) concept from contrastive learning to segment different semantic spaces, each with distinct activation functions. This improves diversity in the feature interaction information captured by the model. Additionally, we introduce self-supervised signals and through connection within each semantic space to ensure the homogeneity of the captured feature interaction information. The experiments conducted on four real datasets demonstrate that our model consistently outperforms twenty baseline models in terms of AUC and Logloss.

Embedding-based recommender systems rely on historical interactions to model users, which poses challenges for recommending to new users, known as the user cold-start problem. Some approaches incorporate social networks to deduce preferences based on the social circles of cold-start users to solve the problem of sparse features. However, such methods have difficulty distinguishing between superficial correlations and causal relationships in social behaviors, leading to inaccuracies in predicting user preferences. To address the aforementioned issues, we propose the Causal Contrastive Learning Recommendation (C2lRec) framework. Specifically, we causally model the inference of hidden preferences from the feature and historical behavior of warm users and predict user interactions based on such preferences. The counterfactual inference is subsequently performed to intervene and extract interactions from historical behaviors of warm users that influence their preferences, designating as primary causal variables. Additionally, we utilize the primary causal variables from users within the social circle of cold-start users to substitute the missing historical interactions of cold-start users and employ a similar causal modeling approach to uncover hidden preferences as we do with warm users. Finally, we realize causal contrastive learning to enhance the distribution of cold-start users. Extensive experiments conducted on three public datasets demonstrate that the recommendation performance of C2lRec exceeds that of state-of-the-art methods.

With the rapid development of the mobile internet, there is an increasing demand for quick access to effective data. Consequently, more research is focusing on data processing and optimization of recommendation systems in edge computing environments. However, in traditional edge computing environments, recommendation systems typically depend on frequent data query interactions among all edge servers to obtain results, which increases time delays. This issue is further exacerbated by the need to process large amounts of data within edge storage systems. To address this challenge, we propose an efficient recommendation method based on data allocation. Specifically, during the data allocation process, we first extract similar features of users, ensuring that the characteristics of some user data align as closely as possible with the overall user feature distribution. Then, using an improved consistent hashing algorithm, we achieve a uniform data layout, allowing the recommendation system to efficiently and accurately provide recommendations by querying data from the nearest edge server to the user. Finally, extensive experiments on real datasets show that our method significantly reduces time delays and improves the accuracy of recommendation results.

Recently, patch-based transformer methods have demonstrated strong effectiveness in time series forecasting. However, the complexity of self-attention imposes demands on memory and compute resources. In addition, though patches can capture comprehensive temporal information while preserving locality, temporal information within patches remains important for time series prediction. The existing methods mainly focus on modeling long-term dependencies across patches, while paying little attention to the short-term dependencies within patches. In this paper, we propose the Global and Local Frequency-domain Network (GLFNet), a novel architecture that efficiently learns global time dependencies and local time relationships in the frequency domain. Specifically, we design a frequency filtering layer to learn the temporal interactions instead of self-attention. Then we devise a dual filtering block consisting of global filter block and local filter block which learns the global dependencies across patches and local dependencies within patches. Experiments on seven benchmark datasets demonstrate that our approach achieve superior performance with improved efficiency.

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions between users are usually complicated rather than pairwise only. Hypergraphs offer a flexible approach to modeling these complex high-order correlations (not just pairwise connections), since hypergraphs can leverage hyperedeges to link more than two nodes. However, most hypergraph-based methods are generic and cannot be well applied to the trust prediction task. In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations. AHNTP utilizes Motif-based PageRank to capture high-order social influence information. In addition, it constructs hypergroups from both node-level and structure-level attributes to incorporate complex correlation information. Furthermore, AHNTP leverages adaptive hypergraph Graph Convolutional Network (GCN) layers and multilayer perceptrons (MLPs) to generate comprehensive user embeddings, facilitating trust relationship prediction. To enhance model generalization and robustness, we introduce a novel supervised contrastive learning loss for optimization. Extensive experiments demonstrate the superiority of our model over the state-of-the-art approaches in terms of trust prediction accuracy.

Anomaly detection is a popular research topic in Artificial Intelligence and has been widely applied in network security, financial fraud detection, and industrial equipment failure detection. Isolation forest based methods are the base algorithms to detect anomalies in these scenarios for their simplicity and efficiency, which has been further exploited with multi-folk trees and learning mechanisms to realize the optimal isolation forest for high detection accuracy. However, the optimal isolation forest is time-consuming with the learning mechanisms, resulting in the task failing of time-constrained applications. Moreover, the original optimal isolation forest fails to construct the optimal tree structure restricted by the time complexity. To address the above challenges, we propose an efficient anomaly detection method called EEIF, which realizes the real e-folk structure of the optimal isolation forest in our practical algorithm design. Specifically, we design a distribution that perfectly matches the e-branch theory to construct the optimal isolation forest. Then, we design an FR clustering scheme to achieve fast training of the isolation forest with learning to hash and provide related proofs of accuracy and efficiency. Besides, a parallel algorithm is integrated into our method to reduce prediction time. Finally, extensive experiments are conducted on a large amount of real-world datasets and the results demonstrate that our method significantly improves efficiency while ensuring effectiveness, compared with the state-of-the-art methods.

Sequential recommendation models generate embeddings for items through the analysis of historical user-item interactions and utilize the acquired embeddings to predict user preferences. Despite being effective in revealing personalized preferences for users, these models heavily rely on user-item interactions. However, due to the lack of interaction information, new users face challenges when utilizing sequential recommendation models for predictions, which is recognized as the cold-start problem. Recent studies, while addressing this problem within specific structures, often neglect the compatibility with existing sequential recommendation models, making seamless integration into existing models unfeasible.To address this challenge, we propose CMCLRec, a Cross-Modal Contrastive Learning framework for user cold-start RECommendation. This approach aims to solve the user cold-start problem by customizing inputs for cold-start users that align with the requirements of sequential recommendation models in a cross-modal manner. Specifically, CMCLRec adopts cross-modal contrastive learning to construct a mapping from user features to user-item interactions based on warm user data. It then generates a simulated behavior sequence for each cold-start user in turn for recommendation purposes. In this way, CMCLRec is theoretically compatible with any extant sequential recommendation model. Comprehensive experiments conducted on real-world datasets substantiate that, compared with state-of-the-art baseline models, CMCLRec markedly enhances the performance of conventional sequential recommendation models, particularly for cold-start users.

Explainable Artificial Intelligence (XAI) aims to make artificial intelligence (AI) systems transparent and understandable to humans, providing clear explanations for the decisions made by AI models. This paper presents a novel pipeline and a digital dashboard that provides a user-friendly platform for interpreting the results of machine learning algorithms using XAI technology. The dashboard utilizes evidence-based design principles to deliver information clearly and concisely, enabling users to better understand the decisions made by their algorithms. We integrate XAI services into the dashboard to explain the algorithm's predictions, allowing users to understand how their models function and make informed decisions. We demonstrate a motivating scenario in banking and present how the proposed system enhances transparency and accountability and improves trust in the technology.

The provision of privacy-preserving recommendations for geological tourist attractions is an important research area. The historical check-in data collected from location-based social networks (LBSNs) can be utilized to mine their preferences, thereby facilitating the promotion of the geological tourism industry. However, such check-ins often contain sensitive user information that poses privacy leakage risks. To address this issue, some methods have been proposed to develop privacy-preserving point-of-interest (POI) recommendation systems. These methods commonly rely on either perturbation-based or federated learning techniques to protect users’ privacy. However, the former can hinder preference capture, while the latter remains vulnerable to privacy breaches during the parameter-sharing process. To overcome these challenges, we propose a novel privacy-preserving POI recommendation model that incorporates users’ privacy preferences based on a simplified graph convolutional neural network. Specifically, we employ a generative model to create a subset of POIs that reflect users’ preferences but do not reveal their private information, and then we design a simplified graph convolutional network to analyze the high-order connectivity between users and POIs that are privacy-preserving. The resulting model enables efficient POI recommendation under strict privacy protection, which is particularly relevant to geological tourism. Experimental results on two public datasets demonstrate the effectiveness of our proposed approach.

Exploring user-item interaction cues is crucial for the performance of recommender systems. Explicit investigation of interaction cues is made possible by using graph-based models, where each user-item relationship is described by an edge, and the introduction of user-user social network. While existing graph-based recommendation methods use only a single-value edge to define the relationship between a pair of user and item, which limits the ability to represent complex user-item interactions. Furthermore, some social recommendation methods overlook the heterogeneous user behavior patterns in social and interaction relationships, resulting in the suboptimal performance of existing systems. In this paper, we propose a novel Social-aware Multi-dimensional Edge Feature-based Graph Representation Learning method, called SMEF. It represents all users and items as a graph and deep learns a multi-dimensional edge feature to explicitly describe the task-specific relationships of each user-item pair. Specifically, the proposed SMEF focuses on two distinct user behavior patterns toward social friends and interactive items, which explore the underlying heterogeneous relationship cues within them. This way, the learned multi-dimensional edge features encode user information from both social and interaction aspects. The proposed SMEF is a plug-and-play module that can be combined with different recommendation frameworks and Graph Neural Networks (GNNs) backbones to generate high quality user representations. The experimental results achieved on three publicly accessible datasets show that our SMEF-based method outperforms strong baselines.

With the exponential growth of mobile devices and the increasing demand for personalized and context-aware services, service-oriented applications play a crucial role in alleviating information overload and improving user experience. At the same time, Edge-Cloud Intelligence (ECI) provides a distributed computing paradigm that leverages the computational capabilities of edge servers to bring services closer to end-users, enabling low-latency and high-bandwidth data processing. The convergence of service applications and ECI has emerged as a promising way to enhance the efficiency and quality of service provisioning in today's dynamic and resource-constrained mobile environment. This call for papers invites researchers and practitioners to contribute to the exploration of the synergy between service applications and ECI infrastructure.

Automatic detection of Cyberbullying is a challenging task due to the availability of limited trained data, which is usually noisy and inherently multimodal. Transfer learning over pre-trained BERT-based language models has succeeded in various complex use cases like sequence-to-sequence translation and text classification. These methods mainly utilize transformer models to learn the word and sentence-level relationships. While they have demonstrated promising results, they only focus on textual features without taking contextual and structural information into account. Moreover, due to the data-heavy nature of BERT-based models, they may fail to model all the desired relationships if not adequate training data is provided to them during the fine-tuning process. In this paper, we propose a novel Session-level Contextualized Transformer-based architecture for Cyberbullying Detection (SECTR-CD), which can leverage transfer learning for modeling word-level attention while also being able to model sentence-level relationships in large bodies of text. The model is also capable of utilizing other contextual features from various modalities like images and social information. Our experimental results indicate remarkable improvement in the Cyberbullying detection task even in the presence of limited training samples.

Text summarization aims to condense text documents into a concise textual summary, which improves the efficiency of people in comprehending information. While deep learning-based summarization methods for individual documents have achieved good performance, there is an increasing demand for summarizing multiple related documents of a topic or event can yield a more coherent and succinct summary of the document set. However, the characteristics of multiple documents with more information, longer texts, and different styles impose new challenges to existing methods in dealing with the multi-aspect of a topic or an event. Therefore, in this paper, we propose a novel multi-granularity model with entity recognition for better sentence ranking and capturing the key information of different documents with a comprehensive and accurate summary. Specifically, we use PRIMERA as a token encoder based on the encoder-decoder framework. Then, a named entity recognition model is trained to identify key elements in documents such as people, location, organization, etc. The proposed model will focus more on these key elements. Based on the named entity recognition results, we further devise a sentence ranking module that allows the model to assign different weights to different sentences based on the sum of the frequencies of the entities contained in the sentences. Finally, based on the results of the multi-granularity encoding vector, the decoder can generate a comprehensive and accurate summary. To evaluate the performance of our proposed model, we conducted experiments on CoNLL2003, DUC2003, and DUC2004, which demonstrated the performance improvement of our proposed method over four previous models.

The pickup and delivery problem (PDP) is considered one of the key optimization problems. PDP is an NP-Hard problem; consequently, researchers tried to solve it using evolutionary algorithms. In literature, different variations of the problem have been studied using evolutionary algorithms. In this paper, we consider the many-objective variation of the PDP known as MaOPDP with six objectives as it is similar to real-life PDP. To solve the problem, we considered 15 different low-level heuristics (LLHs) divided between perturbation and local search phases and optimized the search between LLHs using a cross-domain technique known as Hyper-heuristics (HHs). To effectively solve MaOPDP, a q-learning-based HH named Reinforcement learning-based Selection Hyper-heuristic (RL_SHH) is proposed. According to our knowledge, the considered version of MaOPDP has not been optimized using HHs in the literature. A high-level selection criterion covering exploration and exploitation is proposed to choose between LLHs. To prove the effectiveness of our approach, benchmark data sets have been taken in small, medium, and large sizes and contrasted with state-of-the-art HHs and meta-heuristics. RL-SHH has produced significantly better results on 69 out of 72 instances while using Hypervolume (HV). Additionally, $\mu$ norm mean values (a cross-domain indicator) have been taken into consideration, and RL-SHH has dominated a state-of-the-art HH known as HH-ILS by 646.7% and 100% using HV and Additive Epsilon Indicator (AEI) respectively.

Anomaly detection is one of the crucial research topics in artificial intelligence, encompassing various fields such as health monitoring, network intrusion detection, and fraud detection in financial transactions. Deep anomaly detection (DAD) methods are considered as the effective approaches for addressing complex anomaly detection problems. Among them, the deep isolation forest methods have gained rapid development recently due to their simplicity in parameter turning and efficiency in model training. The existing deep isolation forest approaches are all based on representation learning, while OptiForest theoretically proves the crucial role of the tree structure in isolation forest based methods. In this paper, we analyse the search space of isolation trees under specific data instances and address the challenges in finding optimal isolation forest. Based on the theoretical underpinning and genetic algorithm, we design a deep model DOIForest with two mutation schemes and solution selection, which learns the optimal isolation forest and optimises the parameters in data partitioning. Extensive experiments on both synthetic dataset and a series of real-world datasets demonstrate that our approach can achieve better detection accuracy and robustness than the state-of-the-arts.

Using Web APIs registered in service sharing communities for mobile APP development can not only reduce development period and cost, but also fully reuse state-of-the-art research outcomes in broad domain so as to ensure up-to-date APP development and applications. However, the big volume of available APIs in Web communities as well as their differences make it difficult for APIs selection considering compatibility, preferred partial APIs and expected APIs functions which are often of high variety. Accordingly, how to recommend a set of functional-satisfactory and compatibility-optimal APIs based on the APP developer's multiple function expectation and pre-chosen partial APIs is on demand as a significant challenge for successful APP development. To address this challenge, we first construct a Web APIs correlation graph that incorporates functional descriptions and compatibility information of Web APIs, and then propose a correlation graph-based approach for personalized and compatible Web APIs recommendation in mobile APP development. Finally, through extensive experiments on a real dataset crawled from Web APIs websites, we prove the feasibility of our proposed recommendation approach.

We consider the problem of imitation learning from suboptimal demonstrations that aims to learn a better policy than demonstrators. Previous methods usually learn a reward function to encode the underlying intention of the demonstrators and use standard reinforcement learning to learn a policy based on this reward function. Such methods can fail to control the distribution shift between demonstrations and the learned policy since the learned reward function may not generalize well on out-of-distribution samples and can mislead the agent to highly uncertain states, resulting in degenerated performance. To address this limitation, we propose a novel algorithm called Outperforming demonstrators by Directly Extrapolating Demonstrations(ODED). Instead of learning a reward function, ODED trains an ensemble of extrapolation networks that generate extrapolated demonstrations, i.e., demonstrations that may be induced by a good agent, based on provided demonstrations. With these extrapolated demonstrations, we can use an off-the-shelf imitation learning algorithm to learn a good policy. Guided by extrapolated demonstrations, the learned policy avoids visiting highly uncertain states and therefore controls the distribution shift. Empirically, we show that ODED outperforms suboptimal demonstrators and achieves better performance than state-of-the-art imitation learning algorithms on the MuJoCo and DeepMind Control Suite tasks.

The skyrocketing market value of cryptocurrencies has prompted more investors to pour funds into cryptocurrencies to seek asset hedging. However, the anonymity of blockchain makes cryptocurrency naturally a tool of choice for criminals to commit smart contract scams. Consequently, smart contract scam detection is particularly critical for investors to avoid economic loss. Previous methods mainly leverage specific code logic of smart contracts and/or design rules based on abnormal transaction behaviors for scam detection. Although these methods gain success at detecting particular scams, they perform worse when applied to scams with highly similar codes. Besides, well-designed decision rules rely on expert knowledge and tedious data collection steps, which causes poor flexibility. To combat these challenges, we consider the problem of smart contract scam detection via mining topological features of account interaction information that dynamically evolves. We adopt interactive features extracted from dynamic interaction information of accounts and propose a framework named TTG-SCSD to utilize the features and Topological Data Analysis for smart contract scams detection. The TTG-SCSD constructs discrete dynamic interaction graphs for each contract and designs interactive features that characterize account behaviors. The features are modeled combined with a topology quantification mechanism to capture contract intentions in transactions. Experimental results on real-world transaction datasets from Ethereum show that TTG-SCSD obtains better generalizability and improves the performance of the bare versions of the comparison methods.

Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy utterances, semantic misunderstandings, or lack of knowledge make it hard for a real system to respond properly, possibly leading to an unsatisfactory user experience. To avoid such a case, we consider a proactive interaction mechanism where the system predicts the user satisfaction with the candidate response before giving it to the user. If the user is not likely to be satisfied according to the prediction, the system will ask the user a suitable question to determine the real intent of the user instead of providing the response directly. With such an interaction with the user, the system can give a better response to the user. Previous models that predict the user satisfaction are not applicable to DuerOS which is a large-scale commercial dialogue system. They are based on hand-crafted features and thus can hardly learn the complex patterns lying behind millions of conversations and temporal dependency in multiple turns of the conversation. Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system. To face these challenges, we propose a pipeline to predict the user satisfaction to help DuerOS decide whether to ask for clarification in each turn. Specifically, we propose to first generate a large number of weak labels and then train a transformer-based model to predict the user satisfaction with these weak labels. Moreover, we propose a metric, contextual user satisfaction, to evaluate the experience under the proactive interaction mechanism. At last, we deploy and evaluate our model on DuerOS, and observe a 19% relative improvement on the accuracy of user satisfaction prediction and 2.3% relative improvement on user experience.

Artificial intelligence (AI) enables machines to learn from human experience, adjust to new inputs, and perform intelligent tasks without human intervention. AI is progressing rapidly and is transforming the way businesses operate, from process automation to cognitive augmentation of tasks and intelligent process/data analytics. However, the main challenge for the AI system users is to comprehend and trust the result of AI algorithms and methods. To address this challenge, we first study the recent techniques in the area of eXplainable Artificial Intelligence (XAI). Then, we introduce a novel XAI process to facilitate producing explainable models while maintaining a high level of learning performance. We present an interactive evidence-based approach to assist the users in comprehending and trusting the results and outputs generated by AI-enabled algorithms, resulting in developing a digital dashboard to facilitate inter-acting with the algorithm. Lastly, we discuss how the proposed XAI method can significantly improve the confidence of data scientists in understanding the result of AI-enabled algorithms with an application in the banking domain for analyzing customer transactions.

Mental health disorders may cause severe consequences for countries’ economies and health. Identifying early signs of these disorders is vital. The state-of-the-art research in identifying mental health disorder patterns from textual data, uses hand-labeled training sets, especially when a domain expert’s knowledge is required to analyze various symptoms in a patient. This task could be time-consuming and expensive. To address this challenge, in this paper, we study and analyze the various clinical and non-clinical approaches to identifying mental health disorders. We leverage the domain knowledge and expertise in cognitive science to build a domain-specific Knowledge Base for the mental health disorder concepts and patterns. We present a weaker form of supervision by facilitating and generating training data from a domain-specific Knowledge Base. We adopt a typical scenario for analyzing social media to identify depression symptoms from the textual content generated by social users.

Social trust relationship prediction targets using attributes to quantify the interrelationships in trust between users. Most of the existing algorithms do not consider the heterogeneity and semantics of information included in online social networks, leading to low adaptability in capturing user preferences. What’s more, they only focus on directly connected nodes, and treat all the information propagation paths equally, leading to the lack of structure context information. Given the incomplete graph structure on online social networks constructed by existing algorithms, they can hardly have good performance in the trust prediction. In order to solve the above-mentioned problems, we propose a novel Attention-aware Multi-hop Trust Inference (AMTI) model which could capture different features on both nodes and paths adaptively based on the complex contexts and take multi-hop neighbors into account. Specifically, in our model, we construct a heterogeneous graph of three types of nodes: User, Interest, and Relationship as well as two different meta-paths: User-Interest-User, and User-Relative-User. Then, we adopt a two-level attention mechanism to obtain the attention value on both the node level and path level. To incorporate the multi-hop neighbors’ information, we develop a 2-hop attention diffusion to aggregate the information from the indirectly connected nodes. The experimental results on real-world datasets have demonstrated that AMTI outperforms the state-of-the-art methods in terms of the accuracy of social trust prediction.

We consider an offline reinforcement learning (RL) setting where the agent needs to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. The BC regularizers in many previous methods are mean-seeking, resulting in policies that select out-of-distribution (OOD) actions in the middle of the modes. In this paper, we address both challenges by using adaptively weighted reverse Kullback-Leibler (KL) divergence as the BC regularizer based on the TD3 algorithm. Our method not only trades off the RL and BC signals with per-state weights (i.e., strong BC regularization on the states with narrow action coverage, and vice versa) but also avoids selecting OOD actions thanks to the mode-seeking property of reverse KL. Empirically, our algorithm can outperform existing offline RL algorithms in the MuJoCo locomotion tasks with the standard D4RL datasets as well as the mixed datasets that combine the standard datasets.

With the great success of deep neural networks (DNNs) in a variety of fields, deep learning gains a pioneering development in anomaly detection. Although deep learning achieves good accuracy in anomaly detection, it is troubled with long execution time and high memory consumption. These problems are associated with the inherent drawbacks of deep learning, such as too many parameters and deep training layers. To remedy the above drawbacks, we try to explore an unsupervised non-neural network deep model for anomaly detection based on the experience of the deep forest. In this paper, we propose a deep anomaly detection framework with hashing based isolation forest (DeepiForest) to achieve effective and robust anomaly detection. Specifically, DeepiForest utilizes hashing based isolation forest and tree-embedding scheme to provide enhanced features and apply multi-layer cascaded architecture to establish a deep framework. DeepiForest inherits the advantages of deep forests, i.e., the framework holds fewer hyper-parameters and smaller model complexity than DNNs, simultaneously producing robust accuracy on anomaly detection. Extensive experiments on different-scale datasets illustrate the efficiency of DeepiForest and its comparable effectiveness to the state-of-the-art deep anomaly detection (DAD) methods.

With the ever-increasing popularity of microservice architecture, a considerable number of enterprises or organizations have encapsulated their complex business services into various lightweight functions as published them accessible APIs (Application Programming Interfaces). Through keyword search, a software developer could select a set of APIs from a massive number of candidates to implement the functions of a complex mashup, which reduces the development cost significantly. However, traditional keyword search methods for APIs often suffer from several critical issues such as functional compatibility and limited diversity in search results, which may lead to mashup creation failures and lower development productivity. To deal with these challenges, this paper designs DAWAR, a diversity-aware Web APIs recommendation approach that finds diversified and compatible APIs for mashup creation. Specifically, the APIs recommendation problem for mashup creating is modelled as a graph search problem that aims to find the minimal group Steiner trees in a correlation graph of APIs. DAWAR innovatively employs the determinantal point processes to diversify the recommended results. Empirical evaluation is performed on commonly-used real-world datasets, and the statistic results show that DAWAR is able to achieve significant improvements in terms of recommendation diversity, accuracy, and compatibility.

The widespread use of mobile devices propels the development of new-fashioned video applications like 3D (3-Dimensional) stereo video and mobile cloud game via web or App, exerting more pressure on current mobile access network. To address this challenge, we adopt the crowdsourcing paradigm to offer some incentive for guiding the movement of recruited crowdsourcing users and facilitate the optimization of the movement control decision. In this paper, based on a practical 4G (4th-Generation) network throughput measurement study, we formulate the movement control decision as a cost-constrained user recruitment optimization problem. Considering the intractable complexity of this problem, we focus first on a single crowdsourcing user case and propose a pseudo-polynomial time complexity optimal solution. Then, we apply this solution to solve the more general problem of multiple users and propose a graph-partition-based algorithm. Extensive experiments show that our solutions can improve the efficiency of real-time D2D communication for mobile videos.

The Corona Virus Disease 2019 has a great impact on public health and public psychology. People stay at home for a long time and rarely go out. With the improvement of the epidemic situation, people began to go to different places to check in. To maintain public mental health, it is necessary to propose a point-of-interest (POI) prediction model which can mine users' interests. However, the current techniques suffer from lower precision during prediction and the practical value is poor, which is due to the sparse data of users' check-in. Faced with this challenge, we propose an attention-based bidirectional gated recurrent unit (GRU) model for POI category prediction (ABG_poic). We regard the user's POI category as the user's interest preference because the fuzzy POI category is easier to reflect the user's interest than the POI. This method can alleviate the data sparsity, and protect users' location privacy. Since users' preferences are variable, we utilize a bidirectional GRU to capture the dynamic dependence of users' check-ins. Furthermore, since the neural network is similar to a “black box” in feature learning, the decision-making stage is opaque. Thus, we combine the attention mechanism with bidirectional GRU to selectively focus on historical check-in records, which can improve the interpretability of the model. Considering the time impact on users' check-in, we utilize the time sliding window in the ABG_poic model. Experiments on two data sets demonstrate that our ABG_poic outperforms the comparison models for POI category prediction on sparse check-in data.

Through the collaboration of cloud and edge, cloud-edge computing allows the edge that approximates end-users undertakes those non-computationally intensive service processing of the cloud, reducing the communication overhead and satisfying the low latency requirement of Internet of Vehicle (IoV). With cloud-edge computing, the computing tasks in IoV is able to be delivered to the edge servers (ESs) instead of the cloud and rely on the deployed services of ESs for a series of processing. Due to the storage and computing resource limits of ESs, how to dynamically deploy partial services to the edge is still a puzzle. Moreover, the decision of service deployment often requires the transmission of local service requests from ESs to the cloud, which increases the risk of privacy leakage. In this article, a method for privacy-aware IoV service deployment with federated learning in cloud-edge computing, named PSDF, is proposed. Technically, federated learning secures the distributed training of deployment decision network on each ES by the exchange and aggregation of model weights, avoiding the original data transmission. Meanwhile, homomorphic encryption is adopted for the uploaded weights before the model aggregation on the cloud. Besides, a service deployment scheme based on deep deterministic policy gradient is proposed. Eventually, the performance of PSDF is evaluated by massive experiments.

With the number of users in crowdsourcing increasing rapidly, task matching service is attracting more and more attention. However, it also causes many security concerns, one of which is the leakage of sensitive information. Privacy-preserving task matching techniques can protect the private information of task requesters and workers. Whereas existing privacy-preserving task matching schemes are constructed on a central server, and thereby they may suffer from potential wrongdoings of a malicious server. In addition, most of them only provide accurate task matching, which means that they cannot tolerate keyword spelling errors, leading to the decline of task matching accuracy. In this paper, we propose a Reliable and Privacy-preserving Task Matching scheme (RPTM) for crowdsourcing. To guarantee the reliability of task matching results, RPTM employs smart contracts to ensure that operations of RPTM are faithfully performed. However, it may still disclose the privacy of users due to the transparency of the blockchain. In order to deal with this problem, RPTM can perform task matching service without compromising the privacy of task requesters and workers by leveraging a novel integer vector encryption scheme. Moreover, RPTM supports multi-keyword fuzzy matching by exploiting locality sensitive hashing and Bloom filter, which can tolerate keyword spelling errors and different expression formats. Extensive analysis and experiments based on a test net of EOS show that RPTM is efficient and secure.

While being a lasting theme, privacy, security, and trust (PST) has been increasingly important in recent days due to the pervasive (but more prone) computation infrastructure and deep (but more intrusive) data analytics, and has been hugely demanded from governments, companies, and individuals. This workshop aims at providing a forum for researchers, practitioners and developers from different background areas such as computational intelligence, data privacy and cyber security, trust management, cloud computing, edge computing, Internet of Things, big data analytics, machine learning and data mining, knowledge discovery to exchange the latest experience, research ideas and synergic research and development on fundamental issues and applications about privacy, security and trust issues in computational intelligence.

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership inference attacks (MIAs) that can distinguish the training members of the given model from the non-members. However, existing MIAs ignore the source of a training member, i.e., the information of the client owning the training member, while it is essential to explore source privacy in FL beyond membership privacy of examples from all clients. The leakage of source information can lead to severe privacy issues. For example, identification of the hospital contributing to the training of an FL model for the COVID-19 pandemic can render the owner of a data record from this hospital more prone to discrimination if the hospital is in a high risk region. In this paper, we propose a new inference attack called source inference attack (SIA), which can derive an optimal estimation of the source of a training member. Specifically, we innovatively adopt the Bayesian perspective to demonstrate that an honest-but-curious server can launch an SIA to steal non-trivial source information of the training members without violating the FL protocol. The server leverages the prediction loss of local models on the training members to achieve the attack effectively and non-intrusively. We conduct extensive experiments on one synthetic and five real datasets to evaluate the key factors in an SIA, and the results show the efficacy of the proposed source inference attack.

With the continuous accumulation of users' check-in data, we can gradually capture users' behavior patterns and mine users' preferences. Based on this, the next point-of-interest (POI) recommendation has attracted considerable attention. Its main purpose is to simulate users' behavior habits of check-in behavior. Then, different types of context information are used to construct a personalized recommendation model. However, the users' check-in data are extremely sparse, which leads to low performance in personalized model training using recurrent neural network. Therefore, we propose a category-aware gated recurrent unit (GRU) model to mitigate the negative impact of sparse check-in data, capture long-range dependence between user check-ins and get better recommendation results of POI category. We combine the spatiotemporal information of check-in data and take the POI category as users' preference to train the model. Also, we develop an attention-based category-aware GRU (ATCA-GRU) model for the next POI category recommendation. The ATCA-GRU model can selectively utilize the attention mechanism to pay attention to the relevant historical check-in trajectories in the check-in sequence. We evaluate ATCA-GRU using a real-world data set, named Foursquare. The experimental results indicate that our ATCA-GRU model outperforms the existing similar methods for next POI recommendation.

Anomaly detection is one of the most important data mining tasks in many real-life applications such as network intrusion detection for cybersecurity and medical diagnosis for healthcare. In the big data era, these applications demand fast and versatile anomaly detection capability to handle various types of increasingly huge-volume data. However, existing detection methods are either slow due to high computational complexity, or unable to deal with complicated anomalies like local anomalies. In this paper, we propose a novel anomaly detection method named OPHiForest with the use of the order preserving hashing based isolation forest. The core idea is to learn the information from data to construct better isolation forest structure than the state-of-the-art methods like iForest and LSHiForest, which can achieve robust detection of various anomaly types. We design a fast two-step learning process for the order preserving hashing scheme. This leads to stronger order preservation for better hashing, and therefore enhances anomaly detection robustness and accuracy. Extensive experiments on both synthetic and real-world data sets demonstrate that our method is highly robust and scalable.

Multiple multi-dimensional data streams are ubiquitous in the modern world, such as IoT applications, GIS applications and social networks. Detecting anomalies in such data streams in real-time is an important and challenging task. It is able to provide valuable information from data and then assists decision-making. However, exiting approaches for anomaly detection in multi-dimensional data streams have not properly considered the correlations among multiple multi-dimensional streams. Moreover, for multi-dimensional streaming data, online detection speed is often an important concern. In this paper, we propose a fast yet effective anomaly detection approach in multiple multi-dimensional data streams. This is based on a combination of ideas, i.e., stream pre-processing, locality sensitive hashing and dynamic isolation forest. Experiments on real datasets demonstrate that our approach achieves a magnitude increase in its efficiency compared with state-of-the-art approaches while maintaining competitive detection accuracy.

Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the wellknown Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.

Anomaly or outlier detection is a major challenge in big data analytics because anomaly patterns provide valuable insights for decision-making in a wide range of applications. Recently proposed anomaly detection methods based on the tree isolation mechanism are very fast due to their logarithmic time complexity, making them capable of handling big data sets efficiently. However, the underlying similarity or distance measures in these methods have not been well understood. Contrary to the claims that these methods never rely on any distance measure, we find that they have close relationships with certain distance measures. This implies that the current use of this fast isolation mechanism is only limited to these distance measures and fails to generalise to other commonlyused measures. In this paper, we propose a generic framework named LSHiForest for fast tree isolation based ensemble anomaly analysis with the use of a Locality-Sensitive Hashing (LSH) forest. Being generic, the proposed framework can be instantiated with a diverse range of LSH families, and the fast isolation mechanism can be extended to any distance measures, data types and data spaces where an LSH family is defined. In particular, the instances of our framework with kernelised LSH families or learning based hashing schemes can detect complicated anomalies like local or surrounded anomalies. We also formally show that the existing tree isolation based detection methods are special cases of our framework with the corresponding distance measures. Extensive experiments on both synthetic and real-world benchmark data sets show that the framework can achieve both high time efficiency and anomaly detection quality.

While cloud computing has become an attractive platform for supporting data intensive applications, a major obstacle to the adoption of cloud computing in sectors such as health and defense is the privacy risk associated with releasing datasets to third-parties in the cloud for analysis. A widely-adopted technique for data privacy preservation is to anonymize data via local recoding. However, most existing local-recoding techniques are either serial or distributed without directly optimizing scalability, thus rendering them unsuitable for big data applications. In this paper, we propose a highly scalable approach to local-recoding anonymization in cloud computing, based on Locality Sensitive Hashing (LSH). Specifically, a novel semantic distance metric is presented for use with LSH to measure the similarity between two data records. Then, LSH with the MinHash function family can be employed to divide datasets into multiple partitions for use with MapReduce to parallelize computation while preserving similarity. By using our efficient LSH-based scheme, we can anonymize each partition through the use of a recursive agglomerative $k$-member clustering algorithm. Extensive experiments on real-life datasets show that our approach significantly improves the scalability and time-efficiency of local-recoding anonymization by orders of magnitude over existing approaches.

Outlier detection is an important task in data mining, with applications ranging from intrusion detection to human gait analysis. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version, it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to Incremental LOF but within a fixed memory bound. Our experimental results show that both proposed approaches have better memory and time complexity than Incremental LOF while having comparable accuracy. In addition, we show that MiLOF_F is robust to changes in the number of data points, the number of underlying clusters and the number of dimensions in the data stream. These results show that MiLOF/MiLOF_F are well suited to application environments with limited memory (e.g., wireless sensor networks), and can be applied to high volume data streams.